skill-crawler

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly instructs crawling external documentation with playwright-cli (e.g., "playwright-cli open https://docs.example.com" and snapshot files in Step 1) and then instructs the agent to analyze those extracted snapshots in Step 2, which means untrusted third‑party web content is ingested and can influence generation/decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 10:16 PM